© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71451
    Prev
    Next
    INDEX
    Explanations

    package declarations, names, technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fordshire
    -1.21
     Acesso
    -1.11
     ayaa
    -1.09
    naires
    -1.07
     aí
    -1.05
     času
    -1.04
     triko
    -1.02
    ENDS
    -1.02
     alkoh
    -1.00
    Automation
    -0.99
    POSITIVE LOGITS
    1
    0.97
    2
    0.97
     codzien
    0.97
     U
    0.96
     changed
    0.96
    Hilsen
    0.96
     cemented
    0.95
     M
    0.93
    stddef
    0.93
     igenom
    0.91
    Activations Density 0.000%

    No Known Activations